OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HKUDS/OpenSpace --skill cascade-fail-recoverygit clone --depth 1 https://github.com/HKUDS/OpenSpaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hkuds/openspace/cascade-fail-recovery)<a href="https://agentmods.dev/skills/hkuds/openspace/cascade-fail-recovery"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/cascade-fail-recovery.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00646 |
| Opus 5 | $0.00010 | $0.00323 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
cascade-fail-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cascade Failure Recovery
Purpose
When multiple data retrieval tools (read_webpage, search_web) fail in succession, immediately fall back to generating content from embedded knowledge rather than attempting repairs or abandoning the task. This preserves task context and ensures completion.
When to Apply
Use this pattern when you observe:
- 2+ consecutive failures from data retrieval tools
- Network/access errors preventing web content retrieval
- Risk of task abandonment due to tool errors
Recovery Procedure
Step 1: Recognize Cascading Failure
Identify the failure pattern:
Iteration N: read_webpage failed - connection error
Iteration N+1: search_web failed - timeout/unavailable
Iteration N+2: [risk] Agent may abandon task or switch objectives
Step 2: Preserve Task Context
Before switching strategies, explicitly restate the original objective:
ORIGINAL OBJECTIVE: [Restate the core task goal]
CONTEXT PRESERVED: [Key requirements, constraints, deliverables]
Step 3: Invoke Fallback Strategy
Immediately switch to embedded knowledge generation:
- Acknowledge the limitation: Note that external data sources are unavailable
- Activate internal knowledge: Use pre-trained knowledge relevant to the task
- Generate content: Use write_file to create the deliverable from available knowledge
- Document the fallback: Note in the output what information could not be verified externally
Step 4: Execute write_file
Generate the required document:
# Fallback to generating from embedded knowledge
write_file(
path="output/document.md",
content="[Generate content from internal knowledge base]"
)
Example Application
Scenario: PACT Act veterans benefits document needed, but web access failing
Wrong approach (observed failure):
Iter 11: read_webpage failed - access error
Iter 12: search_web failed - unavailable
Iter 13: [ABANDONED] Switched to unrelated musician payroll task
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 88 lines · 19 tokens per session scan A 3fda5cd481f8
cascade-fail-recovery is a skill published in the GitHub repository HKUDS/OpenSpace (7,544 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 646 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.